Early Fault Detection Method of Rolling Bearing Based on MCNN and GRU Network with an Attention Mechanism

Aiming at the problem of early fault diagnosis rolling bearing, an detection method bearing based on a multiscale convolutional neural network and gated recurrent unit with attention mechanism (MCNN-AGRU) is proposed. This first inputs multiple time scales vibration signals into to train model through data processing then adds make predictive. Finally, reconstruction error between actual value predicted used detect fault. The training this only normal data. in operating condition monitoring performance degradation assessment effectively solved. It uses features extracted by CNN more robust GRU predictive ability not affected length Experimental results show that MCNN-AGRU proposed paper can identify type